Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Ensemble learning”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 127 records · Page 7Linked to original sources
PubMed2000

Encoding of tactile stimulus location by somatosensory thalamocortical ensembles.

The exquisite modular anatomy of the rat somatosensory system makes it an excellent model to test the potential coding strategies used to discriminate the location of a tactile stimulus. Here, we investigated how ensembles of simultaneously recorded single neurons in layer V of primary somatosensory (SI) cortex and in the ventral posterior medial (VPM) nucleus of the thalamus of the anesthetized rat may encode the location of a single whisker stimulus on a single trial basis. An artificial neural network based on a learning vector quantization algorithm, was used to identify putative coding mechanisms. Our data suggest that these neural ensembles may rely on a distributed coding scheme to represent the location of single whisker stimuli. Within this scheme, the temporal modulation of neural ensemble firing rate, as well as the temporal interactions between neurons, contributed significantly to the representation of stimulus location. The relative contribution of these temporal codes increased with the number of whiskers that the ensembles must discriminate among. Our results also indicated that the SI cortex and the VPM nucleus may function as a single entity to encode stimulus location. Overall, our data suggest that the representation of somatosensory features in the rat trigeminal system may arise from the interactions of neurons within and between the SI cortex and VPM nucleus. Furthermore, multiple coding strategies may be used simultaneously to represent the location of tactile stimuli.

Action Potentials↗
PubMed1999

Context-dependent recognition memory: the ICE theory.

A solution to the problem of context-dependent recognition memory is presented in terms of the item, associated context, and ensemble (ICE) theory. It is argued that different types of context effects depend on how context information is encoded at both learning and retrieval. Matching associated context in memory and a retrieval cue produces increases in both hit and false alarm rates and may not be accompanied by a change in discrimination. Integrating item and context information in an ensemble and matching ensemble information in memory and a retrieval cue produces context-dependent discrimination. Empirical support for these predictions is presented.

Adult↗
PubMed2000

Interacting neural networks.

Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random.

Algorithms↗
PubMedDate not supplied

Vector coding and neuronal maps.

A model of vector coding is proposed. An excitation vector is generated in an ensemble of neurons, which has simultaneous actions on the map of selective detectors (selectors), creating a local excitation maximum which represents the input stimulus. Vector coding is also proposed as an explanation for associative learning and memory. Responses to the input in this model are determined by the excitation vectors triggered by command neurons in ensembles of premotor neurons.

Animals↗
PubMed2000

Spatial cognition and neuro-mimetic navigation: a model of hippocampal place cell activity.

A computational model of hippocampal activity during spatial cognition and navigation tasks is presented. The spatial representation in our model of the rat hippocampus is built on-line during exploration via two processing streams. An allothetic vision-based representation is built by unsupervised Hebbian learning extracting spatio-temporal properties of the environment from visual input. An idiothetic representation is learned based on internal movement-related information provided by path integration. On the level of the hippocampus, allothetic and idiothetic representations are integrated to yield a stable representation of the environment by a population of localized overlapping CA3-CA1 place fields. The hippocampal spatial representation is used as a basis for goal-oriented spatial behavior. We focus on the neural pathway connecting the hippocampus to the nucleus accumbens. Place cells drive a population of locomotor action neurons in the nucleus accumbens. Reward-based learning is applied to map place cell activity into action cell activity. The ensemble action cell activity provides navigational maps to support spatial behavior. We present experimental results obtained with a mobile Khepera robot.

Animals↗
PubMed1997

Reconstructing the engram: simultaneous, multisite, many single neuron recordings.

Little is known about the physiological principles that govern large-scale neuronal interactions in the mammalian brain. Here, we describe an electrophysiological paradigm capable of simultaneously recording the extracellular activity of large populations of single neurons, distributed across multiple cortical and subcortical structures in behaving and anesthetized animals. Up to 100 neurons were simultaneously recorded after 48 microwires were implanted in the brain stem, thalamus, and somatosensory cortex of rats. Overall, 86% of the implanted microwires yielded single neurons, and an average of 2.3 neurons were discriminated per microwire. Our population recordings remained stable for weeks, demonstrating that this method can be employed to investigate the dynamic and distributed neuronal ensemble interactions that underlie processes such as sensory perception, motor control, and sensorimotor learning in freely behaving animals.

Animals↗
PubMed1981

Changes in somatosensory evoked potentials during kindling: analogy to learning modifications.

Cortical somatosensory evoked potential (SSEP) changes were studied during kindling of the right pericruciate cortex and in the right hippocampus in 7 cats. The test electric stimuli were delivered to left and right anterior paw. The ipsi- and contralateral SSEPs were averaged before kindling and about every 35th day during kindling. Paroxysmal epileptic discharges developed in all cats. The main consistent changes in all the SSEPs involved components N2-P3-N3, i.e., those with latencies of 90--330 msec. Specifically we noted (1) a gradual decrease in the duration and latency of the N3 component (2) an increase in the slope of the P3-N3 component and (3) a decrease in the duration and latency of the p3 component. These changes were present in both hemispheres, ipsi- and contralateral to both right and left paw stimulation, though favoring the contralateral responses. The changes started to develop before the appearance of spontaneous epileptic activity and seem to be independent of the epileptogenic effect of kindling. Thus, during kindling two types of neuronal function modification seem to take place: epileptogenic and nonepileptogenic. The nonepileptogenic nature of kindling is discussed from the point of view that some forms of learning and kindling are based on similar neurophysiological processes, which lead to permanent neuronal bioelectrical changes. These plastic changes underlie the development of such processes as memory and epilepsy. The difference between these two processes may be in the disturbance of spatiotemporal distribution of coherence in neuronal ensembles.

Animals↗
PubMed1993

On the cerebellum and motor learning.

A critical review of the role of the cerebellum in motor learning is presented. Specifically, the hypothesis that the climbing fibers that issue from the inferior olive serve to modify the responsiveness of cerebellar Purkinje cells is evaluated. It is concluded that there is no convincing evidence, at this time, to support the view that a long-term modification of Purkinje cell activity is either the basis of motor learning or an authentic mechanism of cerebellar function. An alternative view, based on the biophysical, anatomical and ensemble properties of olivary neurons, suggests an important role for the olivocerebellar system in the coordination of movements. Future work in this interesting area of neuroscience will distinguish these two hypotheses.

Animals↗
PubMed2005

Naive coadaptive cortical control.

The ability to control a prosthetic device directly from the neocortex has been demonstrated in rats, monkeys and humans. Here we investigate whether neural control can be accomplished in situations where (1) subjects have not received prior motor training to control the device (naive user) and (2) the neural encoding of movement parameters in the cortex is unknown to the prosthetic device (naive controller). By adopting a decoding strategy that identifies and focuses on units whose firing rate properties are best suited for control, we show that naive subjects mutually adapt to learn control of a neural prosthetic system. Six untrained Long-Evans rats, implanted with silicon micro-electrodes in the motor cortex, learned cortical control of an auditory device without prior motor characterization of the recorded neural ensemble. Single- and multi-unit activities were decoded using a Kalman filter to represent an audio "cursor" (90 ms tone pips ranging from 250 Hz to 16 kHz) which subjects controlled to match a given target frequency. After each trial, a novel adaptive algorithm trained the decoding filter based on correlations of the firing patterns with expected cursor movement. Each behavioral session consisted of 100 trials and began with randomized decoding weights. Within 7 +/- 1.4 (mean +/- SD) sessions, all subjects were able to significantly score above chance (P < 0.05, randomization method) in a fixed target paradigm. Training lasted 24 sessions in which both the behavioral performance and signal to noise ratio of the peri-event histograms increased significantly (P < 0.01, ANOVA). Two rats continued training on a more complex task using a bilateral, two-target control paradigm. Both subjects were able to significantly discriminate the target tones (P < 0.05, Z-test), while one subject demonstrated control above chance (P < 0.05, Z-test) after 12 sessions and continued improvement with many sessions achieving over 90% correct targets. Dynamic analysis of binary trial responses indicated that early learning for this subject occurred during session 6. This study demonstrates that subjects can learn to generate neural control signals that are well suited for use with external devices without prior experience or training.

Action Potentials↗
PubMed2026

Disagreement-informed arbitration for gene regulatory network inference: A score-level meta-classifier and a diagnostic typology of inter-method conflict.

Gene regulatory network inference methods routinely disagree about individual edges, and practitioners resolve those conflicts by choosing one method or averaging them all. We ask whether the conflict can instead be arbitrated per edge. A gradient-boosted classifier is trained on the raw scores that ten inference methods-correlation-based, information-theoretic, sparse-regression and tree-ensemble, including GENIE3, GRNBoost2, CLR and ARACNe-assign to each candidate regulator-target pair, so that the weight given to each method varies from edge to edge. Across six single-cell perturbation screens spanning four cell types, arbitration improves on mean ensembling by +0.056 AUROC on Adamson and +0.083 on Shifrut under target-grouped cross-validation. The evaluation protocol turns out to matter more than the model. Edge-level cross-validation, standard in this literature, inflates apparent gains by 0.060 AUROC through target-gene leakage-comparable to the entire honest improvement. The effect is far larger for methods that represent genes implicitly: a supervised graph-attention link predictor trained on identical folds scores AUROC 0.930 under edge-level cross-validation, better than anything else we evaluate, and 0.533 once target genes are held out. Any method that parameterises genes is exposed, which covers most graph- and embedding-based approaches. A five-category typology of inter-method conflict localises where arbitration pays off, with the largest gains on edges where the methods disagree and the smallest where they already agree, while adding nothing as model input; we therefore report it as a diagnostic instrument rather than a modelling contribution. We also characterise what the ground truth measures: most perturbed genes in widely used screens are not transcription factors, and a mediation screen bounds how much of the perturbation response can be direct.

Ensemble methods↗
PubMed1997

The "independent components" of natural scenes are edge filters.

It has previously been suggested that neurons with line and edge selectivities found in primary visual cortex of cats and monkeys form a sparse, distributed representation of natural scenes, and it has been reasoned that such responses should emerge from an unsupervised learning algorithm that attempts to find a factorial code of independent visual features. We show here that a new unsupervised learning algorithm based on information maximization, a nonlinear "infomax" network, when applied to an ensemble of natural scenes produces sets of visual filters that are localized and oriented. Some of these filters are Gabor-like and resemble those produced by the sparseness-maximization network. In addition, the outputs of these filters are as independent as possible, since this infomax network performs Independent Components Analysis or ICA, for sparse (super-gaussian) component distributions. We compare the resulting ICA filters and their associated basis functions, with other decorrelating filters produced by Principal Components Analysis (PCA) and zero-phase whitening filters (ZCA). The ICA filters have more sparsely distributed (kurtotic) outputs on natural scenes. They also resemble the receptive fields of simple cells in visual cortex, which suggests that these neurons form a natural, information-theoretic coordinate system for natural images.

Algorithms↗
PubMed2005

Dissociating intentional learning from relative novelty responses in the medial temporal lobe.

The establishment of a role for medial temporal lobe (MTL) structures in episodic memory has led to an investigative focus on the specific contributions and interactions between constituent MTL regions, including the hippocampus and surrounding medial temporal cortices. By dissociating an intentional stimulus-category learning condition from a passive viewing condition, we demonstrate, using fMRI, that novelty- and familiarity-driven responses in human anterior and posterior hippocampus, respectively, only occur during intentional learning. With increasing familiarity of stimulus-category associations, there is a shift in neuronal responses from anterior to posterior hippocampal regions. This anterior/posterior response gradient may reflect a weighting of functional hippocampal architecture related to encoding of novel and retrieval of familiar information. By contrast, perirhinal cortex is engaged by novel stimuli irrespective of task, highlighting this region as a component of a generic familiarity discrimination system. By introducing distinct stimulus types, we further demonstrate that these MTL responses are independent of stimulus complexity. Different patterns of activity for intentional learning vs. passive viewing indicate that intentional encoding/retrieval of stimulus-category associations and automatic novelty/familiarity assessment of stimuli are processed in anatomically dissociable neuronal ensembles within the MTL memory system.

Adult↗
PubMed2005

Proteomic mass spectra classification using decision tree based ensemble methods.

MOTIVATION: Modern mass spectrometry allows the determination of proteomic fingerprints of body fluids like serum, saliva or urine. These measurements can be used in many medical applications in order to diagnose the current state or predict the evolution of a disease. Recent developments in machine learning allow one to exploit such datasets, characterized by small numbers of very high-dimensional samples. RESULTS: We propose a systematic approach based on decision tree ensemble methods, which is used to automatically determine proteomic biomarkers and predictive models. The approach is validated on two datasets of surface-enhanced laser desorption/ionization time of flight measurements, for the diagnosis of rheumatoid arthritis and inflammatory bowel diseases. The results suggest that the methodology can handle a broad class of similar problems.

Algorithms↗
PubMed2006

Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room.

OBJECTIVE: Patients with suspicion of acute coronary syndrome (ACS) are difficult to diagnose and they represent a very heterogeneous group. Some require immediate treatment while others, with only minor disorders, may be sent home. Detecting ACS patients using a machine learning approach would be advantageous in many situations. METHODS AND MATERIALS: Artificial neural network (ANN) ensembles and logistic regression models were trained on data from 634 patients presenting an emergency department with chest pain. Only data immediately available at patient presentation were used, including electrocardiogram (ECG) data. The models were analyzed using receiver operating characteristics (ROC) curve analysis, calibration assessments, inter- and intra-method variations. Effective odds ratios for the ANN ensembles were compared with the odds ratios obtained from the logistic model. RESULTS: The ANN ensemble approach together with ECG data preprocessed using principal component analysis resulted in an area under the ROC curve of 80%. At the sensitivity of 95% the specificity was 41%, corresponding to a negative predictive value of 97%, given the ACS prevalence of 21%. Adding clinical data available at presentation did not improve the ANN ensemble performance. Using the area under the ROC curve and model calibration as measures of performance we found an advantage using the ANN ensemble models compared to the logistic regression models. CONCLUSION: Clinically, a prediction model of the present type, combined with the judgment of trained emergency department personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS.

Acute Disease↗
PubMed2005

Progressive transformation of hippocampal neuronal representations in "morphed" environments.

Hippocampal neural codes for different, familiar environments are thought to reflect distinct attractor states, possibly implemented in the recurrent CA3 network. A defining property of an attractor network is its ability to undergo sharp and coherent transitions between pre-established (learned) representations when the inputs to the network are changed. To determine whether hippocampal neuronal ensembles exhibit such discontinuities, we recorded in CA3 and CA1 when a familiar square recording enclosure was morphed in quantifiable steps into a familiar circular enclosure while leaving other inputs constant. We observed a gradual noncoherent progression from the initial to the final network state. In CA3, the transformation was accompanied by significant hysteresis, resulting in more similar end states than when only square and circle were presented. These observations suggest that hippocampal cell assemblies are capable of incremental plastic deformation, with incongruous information being incorporated into pre-existing representations.

Action Potentials↗
PubMed1999

Boosting regression estimators.

There is interest in extending the boosting algorithm (Schapire, 1990) to fit a wide range of regression problems. The threshold-based boosting algorithm for regression used an analogy between classification errors and big errors in regression. We focus on the practical aspects of this algorithm and compare it to other attempts to extend boosting to regression. The practical capabilities of this model are demonstrated on the laser data from the Santa Fe times-series competition and the Mackey-Glass time series, where the results surpass those of standard ensemble average.

Algorithms↗
PubMed1992

A dynamical systems approach to skill acquisition.

This paper argues that the answer to the question, what has to be learned, needs to be established before the question, how is it learned, can be meaningfully addressed. Based on this conviction, some of the limitations of current and past research on skill acquisition are discussed. Motivated by the dynamical systems approach, the question of "what has to be learned" was tackled by setting up a non-linear mathematical model of the task (i.e. learning to make sideways movements on a ski apparatus). On the basis of this model, the phase lag between movements of the platform of the apparatus and the actions of the subject was isolated as an ensemble variable reflecting the timing of the subject in relation to the dynamics of the apparatus. This variable was subsequently used to study "how" the task was learned in a discovery learning experiment, in which predictions stemming from the model were tested and confirmed. Overall, these findings provided support for the hypothesis, formulated by Bernstein (1967), that one of the important effects of practice is learning to make use of reactive forces, thereby reducing the need for active muscular forces. In addition, the data from a previous learning experiment on the ski apparatus--the results of which had been equivocal--were reconsidered. The use of phase lag as a dependent variable provided a resolution of those findings. On the basis of the confirmatory testing of predictions stemming from the model and the clarification of findings from a previous experiment, it is argued that the dynamical systems approach put forward here provides a powerful method for pursuing issues in skill acquisition. Suggestions are made as to how this approach can be used to systematically pursue the questions that arise as a natural outcome of the experimental evidence presented here.

Adult↗